Machine Learning Engineer II (Fraud)

About the Role

The ML Fraud team plays a critical role in Affirm's mission, requiring a balance between technical expertise and collaborative spirit. Your day-to-day activities will involve not only the development of sophisticated models but also the ability to communicate complex ideas to both technical and non-technical stakeholders. The role demands a deep understanding of machine learning principles, strong programming skills, and the ability to navigate and improve upon existing systems.

What You Will Do

• Develop and iterate on fraud prediction models using a mix of approaches for tabular and behavioral data.
• Build and scale feature pipelines and training datasets from proprietary and third-party signals, partnering with data and platform teams when necessary.
• Prototype new modeling ideas and features, run offline experiments, and drive the best-performing approaches into production with appropriate risk controls.
• Help productionize models by integrating them into batch and/or real-time decision systems and improving reliability, latency, and operational robustness.
• Instrument and monitor model and data health, helping define retraining/backtesting workflows as fraud patterns evolve.
• Collaborate across Engineering, Fraud Analytics, Product, and ML Platform to define requirements, evaluate tradeoffs, and communicate results clearly.
• Work on improving the efficiency and effectiveness of the machine learning lifecycle, from data preparation to model deployment.
• Contribute to the development of best practices and standards for machine learning engineering within the company.
• Participate in code reviews, ensuring high-quality code and contributing to the growth of junior engineers.

What We Are Looking For

• A total of 2+ years of experience as a machine learning engineer or a PhD in a relevant field, demonstrating a deep understanding of machine learning principles and practices.
• Strong Python skills and experience writing production-quality code, with the ability to navigate complex codebases.
• Experience building and evaluating models for tabular classification problems, preferably with gradient-boosted decision trees like LightGBM/XGBoost/CatBoost.
• Familiarity with a deep learning framework, with PyTorch being a preferred skill.
• Experience working with distributed data processing or parallel compute frameworks, with Spark being highly desirable.
• Knowledge of ML lifecycle tooling for training orchestration, experimentation, and model monitoring, such as Kubeflow, Airflow, or MLflow.
• Proficiency in using AI-powered developer tools to accelerate iteration, debugging, and code quality.
• Ability to take a simple problem or business scenario and develop it into a solution that interacts with multiple software components, executing on it by writing clear, well-tested, and extensible code.
• Comfort navigating a large code base, debugging others' code, and providing constructive feedback through code reviews.
• Strong verbal and written communication skills that support effective collaboration with a global engineering team.

Nice to Have

• Experience with cloud-based services such as AWS or GCP, particularly in deploying and managing machine learning models.
• Knowledge of containerization using Docker and orchestration with Kubernetes.
• Familiarity with agile development methodologies and version control systems like Git.
• Participation in open-source projects or personal projects that demonstrate machine learning skills.

Benefits and Perks

• Competitive salary and equity package, reflecting Affirm's commitment to attracting and retaining top talent.
• Comprehensive health, dental, and vision insurance for you and your dependents, ensuring your well-being.
• Monthly stipends for health, wellness, and tech spending, supporting your personal and professional growth.
• Access to cutting-edge technologies and tools, enabling you to stay at the forefront of machine learning engineering.
• Remote work flexibility, allowing you to work from anywhere in Canada and maintain a healthy work-life balance.
• Opportunities for professional development and career advancement within a fast-growing company.
• Recognition and reward for outstanding performance, acknowledging your contributions to the company's success.

• Build a strong portfolio: Showcase your machine learning projects, especially those involving fraud detection or similar complex problems, to demonstrate your capabilities to potential employers.
• Stay updated with industry trends: Participate in conferences, meetups, or online forums to stay current with the latest advancements in machine learning and fraud detection.
• Improve your coding skills: Focus on writing clean, efficient, and well-documented code, as this is crucial for success in a machine learning engineering role.
• Prepare for a technical interview: Review common machine learning interview questions and practice coding challenges to ensure you're ready for the technical aspects of the interview process.
• Highlight soft skills: In addition to technical skills, emphasize your ability to work collaboratively, communicate complex ideas effectively, and navigate ambiguity in fast-paced environments.
• Negotiate your salary: Research the market rate for your role and be prepared to negotiate your salary based on your experience and the value you can bring to the company.
• Ask about company culture: During the interview, inquire about the company culture, team dynamics, and opportunities for growth to ensure that the role is a good fit for your career goals and personal values.